(WORK IN PROGRESS) try to tail call address computation w/ more than two args

this folds more stuff, but also finds new breakages

Fixes llvm#136848

Author: zmodem

llvm/lib/Target/X86/X86ISelDAGToDAG.cpp

@@ -897,20 +897,29 @@ static bool isCalleeLoad(SDValue Callee, SDValue &Chain, bool HasCallSeq) {
     Chain = Chain.getOperand(0);
   }
 
-  if (!Chain.getNumOperands())
-    return false;
-  // Since we are not checking for AA here, conservatively abort if the chain
-  // writes to memory. It's not safe to move the callee (a load) across a store.
-  if (isa<MemSDNode>(Chain.getNode()) &&
-      cast<MemSDNode>(Chain.getNode())->writeMem())
+  while (true) {
+    if (!Chain.getNumOperands())
+      return false;
+    // Since we are not checking for AA here, conservatively abort if the chain
+    // writes to memory. It's not safe to move the callee (a load) across a store.
+    if (isa<MemSDNode>(Chain.getNode()) &&
+        cast<MemSDNode>(Chain.getNode())->writeMem())
+      return false;
+
+    if (Chain.getOperand(0).getNode() == Callee.getNode())
+      return true;
+    if (Chain.getOperand(0).getOpcode() == ISD::TokenFactor &&
+        Callee.getValue(1).isOperandOf(Chain.getOperand(0).getNode()) &&
+        Callee.getValue(1).hasOneUse())
+      return true;
+
+    // Look past CopyToReg's.
+    if (Chain.getOperand(0).getOpcode() == ISD::CopyToReg) {
+      Chain = Chain.getOperand(0);
+      continue;
+    }
     return false;
-  if (Chain.getOperand(0).getNode() == Callee.getNode())
-    return true;
-  if (Chain.getOperand(0).getOpcode() == ISD::TokenFactor &&
-      Callee.getValue(1).isOperandOf(Chain.getOperand(0).getNode()) &&
-      Callee.getValue(1).hasOneUse())
-    return true;
-  return false;
+  }
 }
 
 static bool isEndbrImm64(uint64_t Imm) {

llvm/test/CodeGen/X86/cfguard-checks.ll

@@ -210,8 +210,7 @@ entry:
   ; X64-LABEL: vmptr_thunk:
   ; X64:            movq (%rcx), %rax
   ; X64-NEXT:       movq 8(%rax), %rax
-  ; X64-NEXT:       movq __guard_dispatch_icall_fptr(%rip), %rdx
-  ; X64-NEXT:       rex64 jmpq *%rdx            # TAILCALL
+  ; X64-NEXT:       rex64 jmpq *__guard_dispatch_icall_fptr(%rip) # TAILCALL
   ; X64-NOT:   callq
 }
 

llvm/test/CodeGen/X86/fold-call-4.ll

@@ -0,0 +1,16 @@
+; RUN: llc < %s | FileCheck %s
+
+target triple = "x86_64-unknown-linux-gnu"
+
+; The callee address computation should get folded into the call.
+; CHECK-LABEL: f:
+; CHECK-NOT: mov
+; CHECK: jmpq *(%rdi,%rsi,8)
+
+define void @f(ptr %table, i64 %idx) {
+entry:
+  %arrayidx = getelementptr inbounds ptr, ptr %table, i64 %idx
+  %funcptr = load ptr, ptr %arrayidx, align 8
+  tail call void %funcptr(ptr %table, i64 %idx)
+  ret void
+}